RUC's AutoMaster: Skill-guided post-training makes the same model a better teacher

RUC-AIBOX · hf · 2026-11-20

RUC's AutoMaster is an autonomous post-training system built on Skill-FT: natural-language skills steer teacher rollouts to suppress bad habits and elicit underrepresented effective behaviors, then the resulting trajectories fine-tune the target model. An LLM agent handles trajectory analysis, skill design, data selection and feedback. Across Terminal, Search and SWE tasks with 4B/9B models it beats Vanilla SFT on unguided teacher trajectories by 1.42–8.99 points; keeping skill instructions during SFT consistently helps, suggesting better behavioral internalization.

Original post →

More from Research

Research channel →